JPS63298633A - Instruction fetching control system in pipeline processor - Google Patents

Instruction fetching control system in pipeline processor

Info

Publication number
JPS63298633A
JPS63298633A JP13676587A JP13676587A JPS63298633A JP S63298633 A JPS63298633 A JP S63298633A JP 13676587 A JP13676587 A JP 13676587A JP 13676587 A JP13676587 A JP 13676587A JP S63298633 A JPS63298633 A JP S63298633A
Authority
JP
Japan
Prior art keywords
instruction
address
mode
input
psw
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP13676587A
Other languages
Japanese (ja)
Inventor
Aiichiro Inoue
愛一郎 井上
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujitsu Ltd
Original Assignee
Fujitsu Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to JP13676587A priority Critical patent/JPS63298633A/en
Publication of JPS63298633A publication Critical patent/JPS63298633A/en
Pending legal-status Critical Current

Links

Landscapes

  • Advance Control (AREA)

Abstract

PURPOSE:To attain an instruction fetching earlier than the updating of an address designation mode by selecting the designation bit of an address mode at the time of executing the branching instruction to replace the address designating mode and an instruction address. CONSTITUTION:From a part of an adder 6, an input operand before adding is taken out and only the most significant bit MSB to designate an address mode is supplied to a multiplexer 7. A multiplexer 7 is a selector to constitute a selecting means 2 and selects and outputs either of the value of an MSB and the address mode input of a program situation word (PSW) in accordance with the presence and absence of the input of a branch and save and set mode instruction and branch and set mode instruction) BASSM/BSM instruction from a terminal 9. Usually, an adding action is executed in accordance with the address mode input of a PSW, the BASSM/BSM instruction is inputted, and then, the MSB is selected and outputted to an adder 6 and thus, an instruction address is taken out.

Description

【発明の詳細な説明】 〔概要) 本発明は電子計算機を用いたパイプライン処理装置の命
令フ・エッチ制御方式において、命令のオペランドの内
容によりプログラム状況ワード(program 5t
atus word : PSW)内のアドレス指定モ
ードと命令アドレスとをlき換える分岐命令による動作
時に、選択手段により演算手段の一部から取り出した入
力命令中のアドレスモードを指定するビットを演算手段
へ選択出力してアドレス指定モードに応じた命令アドレ
スを生成出力させてプログラム状況ワードのアドレス指
定モードの更新前に命令フェッチを行なうことによより
、 電子計算機の実行速度を速くするようにしたものである
[Detailed Description of the Invention] [Summary] The present invention provides an instruction fetch control method for a pipeline processing device using an electronic computer.
atus word: When operating by a branch instruction that switches the addressing mode and instruction address in the PSW, the selection means selects the bit specifying the address mode in the input instruction extracted from a part of the calculation means to the calculation means. This output generates and outputs an instruction address according to the addressing mode, and fetches the instruction before updating the addressing mode of the program status word, thereby increasing the execution speed of the computer. .

〔産業上の利用分野〕[Industrial application field]

本発明はパイプライン処pH装置における命令フェッチ
制御方式に係り、特に命令のオペランドの内容によりP
SW内のアドレス指定モードと命令アドレスとを行き換
える分岐命令による動作を行なうパイプライン処理装置
における命令フェッチ制御方式に関する。
The present invention relates to an instruction fetch control method in a pipeline processing pH device, and in particular, the present invention relates to an instruction fetch control method in a pipeline processing pH device.
The present invention relates to an instruction fetch control method in a pipeline processing device that performs an operation using a branch instruction that switches between an addressing mode and an instruction address in SW.

電子計算機において、同一の時刻では全回路は夫々別の
データの処理を行なっている(すなわち、並列処理)が
、一つのデータに着目すると、この各部分の処理は順次
引続いて行なわれる(すなわち、直列処理)パイプライ
ン処理が知られている。
In an electronic computer, all circuits process different data at the same time (i.e., parallel processing), but when focusing on one piece of data, each part of the processing is performed sequentially (i.e., parallel processing). , serial processing) pipeline processing is known.

このようなパイプライン処理による高速処理を、より有
効なものにするためには、各命令の処理時間の短縮化が
必要とされる。
In order to make high-speed processing by such pipeline processing more effective, it is necessary to shorten the processing time of each instruction.

〔従来の技術〕 パイプライン処理装置の各命令の中に、PSW内のアド
レス指定モードと命令アドレスを命令のオペランドの内
容で置き換える分岐命令がある。
[Prior Art] Each instruction of a pipeline processing device includes a branch instruction that replaces the addressing mode and instruction address in the PSW with the contents of the operand of the instruction.

この分岐命令には8 A S S M (branch
 and 5aveand set mode)命令及
びB S M (branch and setmod
e )命令がある。これらBASSM命令及び88M命
令は、次命令の7エツチに用いるアドレス指定モードを
変更することになるので、通常の分岐命令の制御の他に
、更新後のアドレス指定モードに従って命令フェッチを
行なう制御が必要になる。
This branch instruction has 8 A S S M (branch
and 5ave and set mode) instructions and BSM (branch and set mode) instructions and BSM (branch and set mode)
e) There is a command. These BASSM and 88M instructions change the addressing mode used for the 7-etch of the next instruction, so in addition to normal branch instruction control, control is required to perform instruction fetch according to the updated addressing mode. become.

第5図は従来方式の一例の動作説明図を承け。FIG. 5 is an explanatory diagram of the operation of an example of the conventional method.

第5図(A)に示すように、マイクロ命令がり。As shown in FIG. 5(A), microinstructions are used.

A、T、B、E及びWの各サイクルの順で処理されるが
、まずDサイクルにて例えば2アドレスコード中の第2
オペランドR2を取り込み、次のへサイクルで加算器(
実効アドレスジェネレータ:EAG)により実効アドレ
スが生成される。
The A, T, B, E, and W cycles are processed in order, but first, in the D cycle, for example, the second of two address codes is processed.
The operand R2 is taken in and the adder (
An effective address is generated by an effective address generator (EAG).

この実行アドレスは第5図(A)に示すように、Aサイ
クルの終りでラッチTOAHにラッチされて次のTサイ
クルの期間保持されてから、そのTサイクルの終りでラ
ッチBOAHにラッチされる。
As shown in FIG. 5A, this execution address is latched into latch TOAH at the end of the A cycle, held for the next T cycle, and then latched into latch BOAH at the end of that T cycle.

このBOΔRでラッチされた実効アドレスはBサイクル
WA間保持され、その終りの時点で次のラッチARC4
にラップされ、次のEサイクルII間保持されて、更に
次のWサイクル期間はラッチARC12に保持され、W
サイクル期間の終りでPSW内に格納される。すなわち
、Wサイクルの終りで、PSW内に新しいアドレス指定
モード(AE)と命令アドレス(JAR)とが格納され
る。
The effective address latched by this BOΔR is held for B cycle WA, and at the end of that period, the next latch ARC4
W is held in the latch ARC12 for the next W cycle period,
Stored in the PSW at the end of the cycle period. That is, at the end of the W cycle, a new addressing mode (AE) and instruction address (JAR) are stored in the PSW.

しかる後に、BASSM/BSM命令では、PSWの7
ドレス指定七−ドと命令アドレスの更新後に、更新後の
アドレス指定モードに従って第5図(B)に示す如く、
1.IT及びIBで示す各サイクルで分岐先命令の7エ
ツチが行なわれる。
After that, in the BASSM/BSM instruction, PSW 7
After updating the address designation code and the instruction address, as shown in FIG. 5(B), according to the updated address designation mode,
1. Seven etches of branch destination instructions are performed in each cycle indicated by IT and IB.

この命令フェッチ後、再び次命令について第5図(A)
と同様のパイプライン処理が行なわれる。
After fetching this instruction, the next instruction is again shown in Fig. 5 (A).
Pipeline processing similar to that is performed.

(発明が解決しようとする問題点〕 従来は上記のRASSM/SSM命令の実行に際し、分
岐先命令のフェッチを、PSWに新しいアドレス指定モ
ードと命令アドレスとを格納した後に行なっていたので
、第5図(A>、(B)に示したように、BASSM/
BSM命令の実行に9サイクルを必要とした。このため
、従来はRASSM/SSM命令の実行時間が長く、パ
イプライン処理の効果が得られないという問題点があっ
た。
(Problems to be Solved by the Invention) Conventionally, when executing the above RASSM/SSM instructions, the branch destination instruction was fetched after storing the new addressing mode and instruction address in the PSW. As shown in figures (A>, (B)), BASSM/
Nine cycles were required to execute the BSM instruction. For this reason, conventionally there has been a problem that the execution time of RASSM/SSM instructions is long and the effects of pipeline processing cannot be obtained.

本発明は上記の点に鑑みて創作されたもので、BASS
M/BSM命令の実行サイクル数が少ないパイプライン
処理装置における命令フェッチ制御方式を提供すること
を目的とする。
The present invention was created in view of the above points, and the BASS
An object of the present invention is to provide an instruction fetch control method in a pipeline processing device in which the number of execution cycles of M/BSM instructions is small.

〔問題点を解決するための手段〕[Means for solving problems]

第1図は本発明の原理ブロック図を示す。同図中、1は
演算手段、2は選択手段、3は格納手段、4はプログラ
ム状況ワード(PSW)である。
FIG. 1 shows a block diagram of the principle of the present invention. In the figure, 1 is an arithmetic means, 2 is a selection means, 3 is a storage means, and 4 is a program status word (PSW).

演算手段1は入力命令から分岐先の命令アドレスを演算
出力する。選択手段2は分岐命令非入力時はPSWのア
ドレスモード入力を演算手段1へ選択出力し、分岐命令
入力時は演算手段1の一部から取り出した入力命令中の
アドレスモードを指定するビットを演算手段1へ選択出
力する。格納手段3は命令アドレスをPSW4に格納す
る。
The calculation means 1 calculates and outputs a branch destination instruction address from an input instruction. The selection means 2 selects and outputs the address mode input of the PSW to the calculation means 1 when a branch instruction is not input, and calculates the bit specifying the address mode in the input instruction taken out from a part of the calculation means 1 when a branch instruction is input. Selectively output to means 1. The storage means 3 stores the instruction address in the PSW 4.

〔作用〕[Effect]

演算手段1により生成された命令アドレスは複数段のラ
ッチからなる格納手段3を転送された後、PSW4に格
納される。
The instruction address generated by the calculation means 1 is transferred to the storage means 3 consisting of a plurality of stages of latches, and then stored in the PSW 4.

ここで、命令のオペランドの内容によりPSW4内のア
ドレス指定モードと命令アドレスとを置き換える分岐命
令入力時には、選択手段2から演算手段1への入力命令
中のアドレスモードを指定するビットの選択人力によっ
て、その分岐命令に従ったアドレスが演算手段1より取
り出される。
Here, when a branch instruction is input to replace the addressing mode in the PSW 4 with the instruction address depending on the contents of the operand of the instruction, the bit specifying the address mode in the input instruction from the selection means 2 to the calculation means 1 is manually selected. The address according to the branch instruction is retrieved from the calculation means 1.

従って、この時に得られる命令アドレスにより命令フェ
ッチを行なうことにより、PSW4のアドレス指定モー
ドの更新より先に命令フェッチができることとなる。
Therefore, by performing an instruction fetch using the instruction address obtained at this time, the instruction can be fetched before the addressing mode of the PSW 4 is updated.

〔実施例〕〔Example〕

第2図は本発明の一実施例のブロック図を示す。 FIG. 2 shows a block diagram of one embodiment of the invention.

同図において、6は前記演算手段1を構成する加算器で
、例えば2アドレスコード中の4バイトの第2オペラン
ドR2をDサイクル期間供給され、その加篩を行なって
第3図(A)に示す如く次のAサイクル期間で命令アド
レスを生成する。ここで、加算器6の一部からは加締前
の、入力オペランドR2が取り出されるが、そのうちア
ドレスモードを指定する最上位ビット(MSB)のみが
マルチプレクサ7に供給される。
In the figure, numeral 6 denotes an adder constituting the arithmetic means 1, which is supplied with, for example, the 4-byte second operand R2 in the 2 address code for a period of D cycles, and performs addition and sieving to produce the result shown in FIG. 3(A). As shown, an instruction address is generated in the next A cycle period. Here, the input operand R2 before caulking is taken out from a part of the adder 6, but only the most significant bit (MSB) specifying the address mode is supplied to the multiplexer 7.

マルチプレクサ7は前記選択手段2を構成するセレクタ
で、上記最上位ビットの値と、端子8よりのPSWのア
ドレスモード入力とのうち、端子9よりのBASSM命
令又は88M命令の入力の有無に応じていずれか一方を
選択出力するよう構成されている。
The multiplexer 7 is a selector constituting the selection means 2, and selects a value according to the value of the most significant bit and the PSW address mode input from the terminal 8, depending on whether the BASSM instruction or the 88M instruction is input from the terminal 9. It is configured to selectively output either one.

すなわち、マルチプレクサ7はBASSM/B8M命令
入力が無いときは、上記AベラノドR2中のMSBから
得たPSWのアドレスモード入力(A E : add
ress extended)を加算器6へ選択出力す
る。このPSWのアドレスモード入力はアドレスモード
を指定する1ビツトの信号で、4バイトの加篩動作を行
なう加算器6の出力オペランドアドレス(命令アドレス
)のうちの有効ビットを指定する。例えばPSWのアド
レスモード人力の値が“1”のときは、加算器6より取
り出される4バイトの命令アドレスのうち、第4図(A
>に模式的に示すように、最上位ビットを除いた31ビ
ツトが有効ビットで、このとき最上位ビットは“0″と
される。また、PSWのアドレスモード入力の値が“O
”のときは、第4図(B)に模式的に示すよう、下位2
4ビツトが有効ビットで、残りの上位8ビツトが“0”
とされる。
That is, when there is no BASSM/B8M command input, the multiplexer 7 inputs the PSW address mode input (A E : add
ress extended) is selectively output to the adder 6. The address mode input of this PSW is a 1-bit signal that specifies the address mode, and specifies the valid bit of the output operand address (instruction address) of the adder 6 that performs a 4-byte sifting operation. For example, when the value of the PSW address mode manual is "1", of the 4-byte instruction address taken out from the adder 6, the
>, 31 bits excluding the most significant bit are valid bits, and at this time the most significant bit is set to "0". Also, the value of the PSW address mode input is “O”.
”, as shown schematically in Figure 4 (B), the lower 2
4 bits are valid bits, remaining upper 8 bits are “0”
It is said that

通常はこのPSWのアドレスモード入力に従った加算動
作が行なわれるが、BASSM/BSM命令が入力され
ると、マルチプレクサ7は上記加算器6の一部より取り
出されたMSBの値を加算器6へ選択出力する。これに
より、加算器6からはそのMSBの値に応じて第4図(
A)又は(B)に示すように、下位31ビツト又は下位
 24ビツトを命令アドレスとし、残りの上位ビットが
“0”とされた命令アドレスが取り出される。
Normally, an addition operation is performed according to the address mode input of this PSW, but when a BASSM/BSM command is input, the multiplexer 7 transfers the MSB value extracted from a part of the adder 6 to the adder 6. Selectively output. As a result, the adder 6 outputs data according to the value of the MSB as shown in FIG.
As shown in A) or (B), the lower 31 bits or lower 24 bits are used as an instruction address, and the instruction address with the remaining upper bits set to "0" is extracted.

加算器6より取り出された命令アドレスは、Aサイクル
期間の終りでラッチ動作を行なうラッチ(TOAR)1
0、Tサイクル期間の終りでラッチ動作を行なうラッチ
(BORA)1 L Bサイクル期間の終りでラップ動
作を行なうラップ(EOAR)12、及びEサイクル期
間の終りでラッチ動作を行なうラップ(WOAR)13
により、順次ラッチされる。
The instruction address taken out from the adder 6 is stored in latch (TOAR) 1, which performs a latch operation at the end of the A cycle period.
0, Latch (BORA) 1 that performs a latch operation at the end of the T cycle period, Wrap (EOAR) 12 that performs a wrap operation at the end of the B cycle period, and Wrap (WOAR) 13 that performs a latch operation at the end of the E cycle period.
are latched sequentially.

これにより、第3図(A)に模式的に示すように、加算
器6の出力命令アドレスは、ラッチ10゜11.12及
び13により1サイクル明間ずつ保持され、かつ、順次
ラッチ13方向へ転送されていき、Wサイクル期間の終
りでPSW内に格納される。また、このとき、別系統で
伝送された新しいアドレス指定モード1ビツトがPSW
内に格納される。
As a result, as schematically shown in FIG. 3(A), the output instruction address of the adder 6 is held by the latches 10, 11, 12, and 13 for one cycle at a time, and is sequentially moved toward the latch 13. It is transferred and stored in the PSW at the end of the W cycle period. Also, at this time, the new addressing mode 1 bit transmitted in another system is set to PSW.
stored within.

ここで、BASSM/BSM命令時には、アド命令権定
モードが第4図(B)に示した24ビツトモードで、加
算器6の最終出力端よりΔサイクル期間で取り出される
命令アドレスはその後のWサイクル期間の終りでPSW
内の命令アドレスに置き換えられるが、それ以前のAサ
イクル期間内でこのときの命令アドレスを用いて第3図
(B)に模式的に示す如く命令フェッチが行なわれる。
Here, at the time of the BASSM/BSM instruction, the add instruction authority mode is the 24-bit mode shown in FIG. PSW at the end of
However, during the previous A cycle period, the instruction address at this time is used to perform an instruction fetch as schematically shown in FIG. 3(B).

従って、本実施例によれば、PSWのアドレス指定モー
ドの更新より先に命令フェッチが可能なので、第3図(
B)に示すように、次命令の処理が開始されるまで、4
サイクルで済む。
Therefore, according to this embodiment, the instruction can be fetched before the PSW addressing mode is updated.
4 until the next instruction starts processing, as shown in B).
It's a cycle.

なお、このとき行なわれる制御のうち、アドレス生成の
ための加算器6の出力を命令フェッチに回して、分岐先
命令の先取りをする制御は従来から実用化されている。
Among the controls performed at this time, control in which the output of the adder 6 for address generation is sent to instruction fetch to prefetch the branch destination instruction has been put to practical use.

しかし、この場合はアドレス指定モードがPSWのアド
レスモード入力に従って行なわれるのに対し、本実施例
では加算器6を32ビツトフルで演算動作するようにし
ておき、その出力のMSBに従ったアドレス指定モード
で■フェッチを行なう点が異なる。
However, in this case, the addressing mode is performed according to the address mode input of the PSW, whereas in this embodiment, the adder 6 is set to operate at full 32 bits, and the addressing mode is performed according to the MSB of the output. The difference is that ■ fetch is performed.

〔発明の効果〕〔Effect of the invention〕

上述の如く、本発明によれば、PSWのアドレス指定モ
ードの更新より先に命令フェッチを行なうようにしたの
で、従来にくらべてBASSM/SSM命令の実行時間
を短縮化でき、これにより所要のパイプラインの効果を
得ることができる等の特長を有するものである。
As described above, according to the present invention, since the instruction fetch is performed before updating the PSW addressing mode, the execution time of the BASSM/SSM instruction can be shortened compared to the conventional method. It has features such as being able to obtain a line effect.

【図面の簡単な説明】[Brief explanation of drawings]

第1図は本発明の原理ブロック図、 第2図は本発明の一実施例のブロック図、第3図は本発
明の一実施例の動作説明図、第4図は命令アドレスの各
例の説明図、第5図は従来の一例の動作説明図である。 図中において、 1は演算手段、 2は選択手段、 3は格納手段0. 4はプログラム状況ワード(PSW)、6は加算器、 7はマルチプレクサ、 10〜13はラッチである。 、−一 本発矧f)原理ブロイ2図 第1図 本有しtの一宍3拒澄νコのプ°ローノ2町第2図
Fig. 1 is a block diagram of the principle of the present invention, Fig. 2 is a block diagram of an embodiment of the invention, Fig. 3 is an explanatory diagram of the operation of an embodiment of the invention, and Fig. 4 is a diagram of each example of instruction address. The explanatory diagram, FIG. 5, is an explanatory diagram of the operation of an example of the conventional system. In the figure, 1 is a calculation means, 2 is a selection means, 3 is a storage means 0. 4 is a program status word (PSW), 6 is an adder, 7 is a multiplexer, and 10 to 13 are latches. ,-Ippon-Hatsuhaf) Principle Broken 2 Diagram 1 Figure 1 Book has t Ichishi 3 Refusal ν Co's Prono 2 Town Diagram 2

Claims (1)

【特許請求の範囲】  命令のオペランドの内容によりプログラム状況ワード
(PSW)(4)内のアドレス指定モードと命令アドレ
スとを置き換える分岐命令による動作を行なうパイプラ
イン処理装置において、分岐先の上記命令アドレスを入
力命令から演算出力する演算手段(1)と、 前記分岐命令非入力時はプログラム状況ワード(4)の
アドレスモード入力を前記演算手段(1)へ選択出力し
、該分岐命令入力時は該演算手段(1)の一部から取り
出した前記入力命令中のアドレスモードを指定するビッ
トを該演算手段(1)へ選択出力して該演算手段(1)
より該アドレス指定モードに応じた命令アドレスを生成
出力させる選択手段(2)と、 該演算手段(1)の出力命令アドレスを複数段のラッチ
を順次転送して前記プログラム状況ワード(4)に格納
する格納手段(3)とよりなり、前記分岐命令入力時は
該演算手段(1)より取り出された該命令アドレスによ
って前記プログラム状況ワード(4)のアドレス指定モ
ードの更新前に命令フェッチを行なうことを特徴とする
パイプライン処理装置における命令フェッチ制御方式。
[Claims] In a pipeline processing device that performs an operation using a branch instruction in which the addressing mode and instruction address in a program status word (PSW) (4) are replaced depending on the contents of the operand of the instruction, the instruction address of the branch destination is an arithmetic means (1) for calculating and outputting from an input instruction, and selectively outputting an address mode input of a program status word (4) to the arithmetic means (1) when the branch instruction is not input; Selectively outputting a bit specifying an address mode in the input instruction extracted from a part of the arithmetic means (1) to the arithmetic means (1);
a selection means (2) for generating and outputting an instruction address according to the addressing mode; and a selection means (2) for sequentially transferring the output instruction address of the calculation means (1) through a plurality of latches and storing it in the program status word (4). and a storage means (3) for performing an instruction fetch before updating the addressing mode of the program status word (4) by the instruction address retrieved from the arithmetic means (1) when the branch instruction is input. An instruction fetch control method in a pipeline processing device characterized by:
JP13676587A 1987-05-29 1987-05-29 Instruction fetching control system in pipeline processor Pending JPS63298633A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP13676587A JPS63298633A (en) 1987-05-29 1987-05-29 Instruction fetching control system in pipeline processor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP13676587A JPS63298633A (en) 1987-05-29 1987-05-29 Instruction fetching control system in pipeline processor

Publications (1)

Publication Number Publication Date
JPS63298633A true JPS63298633A (en) 1988-12-06

Family

ID=15182985

Family Applications (1)

Application Number Title Priority Date Filing Date
JP13676587A Pending JPS63298633A (en) 1987-05-29 1987-05-29 Instruction fetching control system in pipeline processor

Country Status (1)

Country Link
JP (1) JPS63298633A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7036003B1 (en) 1999-09-29 2006-04-25 Fujitsu Limited Instruction processing device and method for controlling branch instruction accompanied by mode change
US7502725B2 (en) 2004-04-29 2009-03-10 International Business Machines Corporation Method, system and computer program product for register management in a simulation environment

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS60142742A (en) * 1983-12-29 1985-07-27 Hitachi Ltd Data processing unit

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS60142742A (en) * 1983-12-29 1985-07-27 Hitachi Ltd Data processing unit

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7036003B1 (en) 1999-09-29 2006-04-25 Fujitsu Limited Instruction processing device and method for controlling branch instruction accompanied by mode change
US7502725B2 (en) 2004-04-29 2009-03-10 International Business Machines Corporation Method, system and computer program product for register management in a simulation environment
US7720669B2 (en) 2004-04-29 2010-05-18 International Business Machines Corporation Method, system and computer program product for register management in a simulation environment

Similar Documents

Publication Publication Date Title
JPH11154114A (en) System and method for table look-up using architecture of plural data fetching
US4658355A (en) Pipeline arithmetic apparatus
JPH05216624A (en) Arithmetic unit
JPS6217252B2 (en)
JPS633337B2 (en)
US4954947A (en) Instruction processor for processing branch instruction at high speed
JPS6015745A (en) Information processor
JPH03286332A (en) Digital data processor
JPH04245324A (en) Arithmetic unit
JPH0418635A (en) Digital signal processor
JPS63298633A (en) Instruction fetching control system in pipeline processor
JPH0640337B2 (en) Pipeline arithmetic unit
JPH0512009A (en) Digital signal processing device
JPH0233173B2 (en)
JPS59184944A (en) Rounding arithmetic system
JPS58200349A (en) Microprogram controller
JP2843844B2 (en) Parallel processing unit
JP5263498B2 (en) Signal processor and semiconductor device
JPS6116334A (en) Data processor
KR100303136B1 (en) Structure for microprocessor having digital signal processor
JPH01287742A (en) Immediate instruction processing system
US5822775A (en) Efficient data processing method for coefficient data in a digital dignal, processor
JP2583614B2 (en) Vector arithmetic unit
JPH02249025A (en) Signal processor
JPH01147723A (en) Pipe line processing system for information processor